Towards Artificial Emotions to Assist Social Coordination in HRI
Towards Artificial Emotions to Assist Social Coordination in HRI
复制标题
DOI：
10.1007/s12369-014-0254-y
复制
发表时间：
2015-02-01
影响因子：
4.7
通讯作者：
Watts, Leon
中科院分区：
文献类型：
--
作者：
Novikova, Jekaterina;Watts, Leon
人-机器人联合活动的协调必须依赖于人类和人工机构解释和交织其行动的能力。在本文中，我们考虑了人工情感作为人机团队中任务相关协调设备的潜力。我们提出了两项研究，旨在了解非人形机器人是否能够以对人类观察者有意义的方式表达人工情感，第一项研究基于静态图像，第二项研究基于具身机器人表情的动态产生。我们提出了一种混合方法来解决这个问题，将评级数据的统计处理和定性数据的专题分析相结合。我们的研究结果表明，即使是非人形机器人的非常简单的动作也可以传达情感含义，当人们将情感状态归因于机器人时，他们通常会应用基于事件的框架来理解他们所看到的机器人表情。与具有正效价的情绪相比，具有高唤醒水平和负效价的人工情绪更容易被人们识别。我们讨论了在非人形机器人身体的不同部位使用运动来支持HRI中情感归因的可能性，以及在道德上负责任的人工情感设计，这可能有助于人类-机器人联合活动的功效。
Coordination of human-robot joint activity must depend on the ability of human and artificial agencies to interpret and interleave their actions. In this paper we consider the potential of artificial emotions to serve as task-relevant coordination devices in human-robot teams. We present two studies aiming to understand whether a non-humanoid robot can express artificial emotions in a manner that is meaningful to a human observer, the first based on static images and the second on the dynamic production of embodied robot expressions. We present a mixed-methods approach to the problem, combining statistical treatment of ratings data and thematic analysis of qualitative data. Our results demonstrate that even very simple movements of a non-humanoid robot can convey emotional meaning, and that when people attribute emotional states to a robot, they typically apply an event-based frame to make sense of the robotic expressions they have seen. Artificial emotions with high arousal level and negative valence are relatively easy for people to recognise compared to expressions with positive valence. We discuss the potential for using motion in different parts of a non-humanoid robot body to support the attribution of emotion in HRI, towards ethically responsible design of artificial emotions that could contribute to the efficacy of joint human-robot activities.